Prediction of postoperative infection in elderly using deep learning-based analysis: an observational cohort study
Pinhao Li, Yan Wang, Hui Li, Baoli Cheng, Shuijing Wu, Hui Ye, Daqing Ma, Xiangming Fang, the International Surgical Outcomes Study (ISOS) group in China, Ying Cao, Hong Gao, Tingju Hu, Jie Lv, Jian Yang, Yang Yang, Yi Zhong, Jing Zhou, Xiaohua Zou, Miao He, Xiaoying Li, Dihuan Luo, Haiying Wang, Tian Yu, Liyong Chen, Lijun Wang, Yunfei Cai, Zhongming Cao, Yanling Li, Jiaxin Lian, Haiyun Sun, Sheng Wang, Zhipeng Wang, Kenru Wang, Yi Zhu, Xindan Du, Hao Fan, Yunbin Fu, Lixia Huang, Yanming Huang, Haifang Hwan, Luo Hong, Pi-Sheng Qu, Tao Fan, Zhen Wang, Guoxiang Wang, Shun Wang, Yan Zhang, Xiaolin Zhang, Chao Chen, Weixing Wang, Zhengyuan Liu, Lihua Fan, Jing Tang, Yijun Chen, Yongjie Chen, Yangyang Han, Changshun Huang, Guojin Liang, Jing Shen, Jun Wang, Qiuhong Yang, Jungang Zhen, Haidong Zhou, Junping Chen, Zhang Chen, Xiaoyu Li, Bo Meng, Haiwang Ye, Xiaoyan Zhang, Yanbing Bi, Jianqiao Cao, Fengying Guo, Hong Lin, Yang Liu, Meng Lv, Pengcai Shi, Xiumei Song, Chuanyu Sun, Yongtao Sun, Yuelan Wang, Shenhui Wang, Min Zhang, Rong Chen, Jiabao Hou, Yan Leng, Qingtao Meng, Li Qian, Zi-ying Shen, Zhongyuan Xia, Rui Xue, Yuan Zhang, Bo Zhao, Xianjin Zhou, Qiang Chen, Huinan Guo, Yongqing Guo, Yuehong Qi, Zhi Wang, Jianfeng Wei, Weiwei Zhang
Abstract
Elderly patients are susceptible to postoperative infections with increased mortality. Analyzing with a deep learning model, the perioperative factors that could predict and/or contribute to postoperative infections may improve the outcome in elderly. This was an observational cohort study with 2014 elderly patients who had elective surgery from 28 hospitals in China from April to June 2014. We aimed to develop and validate deep learning-based predictive models for postoperative infections in the elderly. 1510 patients were randomly assigned to be training dataset for establishing deep learning-based models, and 504 patients were used to validate the effectiveness of these models. The conventional model predicted postoperative infections was 0.728 (95% CI 0.688-0.768) with the sensitivity of 66.2% (95% CI 58.2-73.6) and specificity of 66.8% (95% CI 64.6-68.9). The deep learning model including risk factors relevant to baseline clinical characteristics predicted postoperative infections was 0.641 (95% CI 0.545-0.737), and sensitivity and specificity were 34.2% (95% CI 19.6-51.4) and 88.8% (95% CI 85.6-91.6), respectively. Including risk factors relevant to baseline variables and surgery, the deep learning model predicted postoperative infections was 0.763 (95% CI 0.681-0.844) with the sensitivity of 63.2% (95% CI 46-78.2) and specificity of 80.5% (95% CI 76.6-84). Our feasibility study indicated that a deep learning model including risk factors for the prediction of postoperative infections can be achieved in elderly. Further study is needed to assess whether this model can be used to guide clinical practice to improve surgical outcomes in elderly.